Abstract
Instruments based on light scattering used to measure total suspended particulate (TSP) concentrations have the advantages of fast response, small size, and low cost compared to the gravimetric reference method. However, the relationship between scattering intensity and TSP mass concentration varies nonlinearly with both environmental conditions and particle properties, making it difficult to make corrections. This study applied four machine learning models (support vector machines, random forest, gradient boosting regression trees, and an artificial neural network) to correct scattering measurements for TSP mass concentrations. A total of 1141 hourly records of collocated gravimetric and light scattering measurements taken at 17 urban sites in Shanghai, China were used for model training and validation. All four machine learning models improved the linear regressions between scattering and gravimetric mass by increasing slopes from 0.4 to 0.9–1.1 and coefficients of determination from 0.1 to 0.8–0.9. Partial dependence plots indicate that TSP concentrations determined by light scattering instruments increased continuously in the PM2.5 concentration range of ~0–80 µg/m3; however, they leveled off above PM10 and TSP concentrations of ~60 and 200 µg/m3, respectively. The TSP mass concentrations determined by scattering showed an exponential growth after relative humidity exceeded 70%, in agreement with previous studies on the hygroscopic growth of fine particles. This study demonstrates that machine learning models can effectively improve the correlation between light scattering measurements and TSP mass concentrations with filter-based methods. Interpretation analysis further provides scientific insights into the major factors (e.g., hygroscopic growth) that cause scattering measurements to deviate from TSP mass concentrations besides other factors like fluctuation of mass density and refractive index.
Highlights
Total suspended particulate (TSP) generally refers to particulate matter suspended in air with an aerodynamic equivalent diameter of less than 100 μm
This study aims to develop and validate machine learning models to correct light scattering instruments that report total suspended particulate (TSP) mass concentrations
The input variables included the hourly TSP mass concentrations from the Casella raw readings based on light scattering obtained at each site, criteria pollutant concentrations from the nearest national monitoring stations (PM2.5, PM10, SO2, NO2, CO, and O3 ), ambient temperature, and relative humidity (RH) (Table 2)
Summary
Total suspended particulate (TSP) generally refers to particulate matter suspended in air with an aerodynamic equivalent diameter of less than 100 μm. The TEOM method is based on the principle of frequency changes when the oscillation element is loaded with particles, while the β-ray method estimates PM mass loading based on β-ray energy attenuation across a PM loaded filter [2,3,4] These two methods are usually accurate and the time resolution can be as high as a few minutes; the large size and high cost of these instruments limit their wide application. Due to its wide size range, TSP has more diverse particle physical and chemical properties, which lead to more complicated hygroscopic effects, making the correction of TSP mass concentrations reported by light scattering instrument more challenging. This study aims to develop and validate machine learning models to correct light scattering instruments that report TSP mass concentrations. Partial dependence plots were used to interpret factors (e.g., hygroscopic growth) affecting the model outputs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
